Compare commits

..

22 Commits

Author SHA1 Message Date
Andrew Kane
4b2c593873 Updated number of parallel workers for IVFFlat index builds 2024-02-28 15:03:50 -08:00
Andrew Kane
447ef4d27a Specify Postgres version for Valgrind [skip ci] 2024-02-28 14:16:48 -08:00
Andrew Kane
b36cd22ccc Enable assertions on CI 2024-02-28 14:15:34 -08:00
Andrew Kane
b447ae4989 Avoid base address for relptr for Postgres < 14.5 2024-02-28 14:10:14 -08:00
Andrew Kane
efed873a3e Revert "Replaced pairing heap with array in SelectNeighbors - closes #447"
This reverts commit 14b278dec9.
2024-02-28 11:33:14 -08:00
Andrew Kane
14b278dec9 Replaced pairing heap with array in SelectNeighbors - closes #447
Co-authored-by: Heikki Linnakangas <heikki.linnakangas@iki.fi>
2024-02-28 11:25:12 -08:00
Andrew Kane
133a728e48 Updated changelog [skip ci] 2024-02-20 16:38:05 -08:00
Andrew Kane
ca10cbaa7d Revert "Remove offsethash"
This reverts commit 1cbd204f52.
2024-02-20 16:07:32 -08:00
Andrew Kane
eb29019a14 Revert "Eliminate a few HnswPtrAccess invocations"
This reverts commit 334c386a45.
2024-02-20 16:07:21 -08:00
Heikki Linnakangas
334c386a45 Eliminate a few HnswPtrAccess invocations
HnswPtrAccess() is pretty cheap, but it stills seems worthwhile to
avoid repeated calls in the hot paths when it can be easily avoided.
2024-02-19 14:13:18 +02:00
Heikki Linnakangas
1cbd204f52 Remove offsethash
The original motivation was to eliminate the superfluous HnswPtrAccess
call from AddToVisited. The caller has to call HnswPtrAccess() anyway,
so it makes sense to pass the HnswElement rather than HnswElementPtr
to AddToVisited(). But then I realized that we can use the
pointer-variant even with shared memory, because the visited-hash is
backend-private, and the addresses where the elements are mapped to in
shared memory are stable within the backend.
2024-02-19 14:12:26 +02:00
Andrew Kane
5ba62fca84 Fixed crash with shared_preload_libraries - fixes #460 2024-02-14 17:13:30 -08:00
Andrew Kane
22cb2a3fe7 Simplified Docker tasks [skip ci] 2024-02-07 12:03:33 -08:00
Andrew Kane
72b144906a Added Valgrind to CI 2024-02-07 09:43:01 -08:00
Andrew Kane
a618c1bc78 Updated port name [skip ci] 2024-02-06 12:43:20 -08:00
Andrew Kane
f43cd0ed98 Improved type [skip ci] 2024-02-05 19:38:52 -08:00
Andrew Kane
51df640961 Added instructions for pkg [skip ci] 2024-02-05 17:01:36 -08:00
Andrew Kane
2716a223a6 Fixed error with ANALYZE and vectors with different dimensions - fixes #451 2024-02-02 10:47:48 -08:00
Andrew Kane
3697043898 Added note about vacuuming - closes #450 [skip ci] 2024-01-31 14:35:27 -08:00
Andrew Kane
c22740962c Added note for Docker [skip ci] 2024-01-29 15:33:29 -08:00
Andrew Kane
a55ecf3281 Updated changelog [skip ci] 2024-01-29 11:20:33 -08:00
Andrew Kane
fecdd5794e Updated readme [skip ci] 2024-01-29 10:57:54 -08:00
11 changed files with 177 additions and 17 deletions

View File

@@ -28,7 +28,7 @@ jobs:
dev-files: true
- run: make
env:
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
- run: |
export PG_CONFIG=`which pg_config`
sudo --preserve-env=PG_CONFIG make install
@@ -49,7 +49,7 @@ jobs:
postgres-version: 14
- run: make
env:
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
- run: make install
- run: make installcheck
- if: ${{ failure() }}
@@ -97,4 +97,15 @@ jobs:
sudo -u postgres make installcheck
sudo -u postgres make prove_installcheck
env:
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
valgrind:
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: ankane/setup-postgres-valgrind@v1
with:
postgres-version: 16
- run: make
- run: sudo --preserve-env=PG_CONFIG make install
- run: make installcheck

View File

@@ -1,10 +1,15 @@
## 0.6.1 (unreleased)
- Fixed error with `ANALYZE` and vectors with different dimensions
- Fixed error with `shared_preload_libraries`
## 0.6.0 (2024-01-29)
If upgrading with Postgres 12 or Docker, see [these notes](https://github.com/pgvector/pgvector#060).
- Changed storage for vector from `extended` to `external`
- Added support for parallel index builds for HNSW
- Added validation for GUC parameters
- Changed storage for vector from `extended` to `external`
- Improved performance of HNSW
- Reduced memory usage for HNSW index builds
- Reduced WAL generation for HNSW index builds

View File

@@ -71,11 +71,9 @@ PG_MAJOR ?= 16
.PHONY: docker
docker:
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
docker build --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
.PHONY: docker-release
docker-release:
docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
docker buildx build --push --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .

View File

@@ -16,7 +16,7 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
### Linux and Mac
Compile and install the extension (supports Postgres 11+)
Compile and install the extension (supports Postgres 12+)
```sh
cd /tmp
@@ -28,7 +28,7 @@ make install # may need sudo
See the [installation notes](#installation-notes) if you run into issues
You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), [pkg](#pkg), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
### Windows
@@ -430,6 +430,15 @@ To speed up queries with an IVFFlat index, increase the number of inverted lists
CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 1000);
```
## Vacuuming
Vacuuming can take a while for HNSW indexes. Speed it up by reindexing first.
```sql
REINDEX INDEX CONCURRENTLY index_name;
VACUUM table_name;
```
## Languages
Use pgvector from any language with a Postgres client. You can even generate and store vectors in one language and query them in another.
@@ -657,7 +666,7 @@ Get the [Docker image](https://hub.docker.com/r/pgvector/pgvector) with:
docker pull pgvector/pgvector:pg16
```
This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (run it the same way).
This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (replace `16` with your Postgres server version, and run it the same way).
You can also build the image manually:
@@ -707,6 +716,21 @@ sudo dnf install pgvector_16
Note: Replace `16` with your Postgres server version
### pkg
Install the FreeBSD package with:
```sh
pkg install postgresql15-pg_vector
```
or the port with:
```sh
cd /usr/ports/databases/pgvector
make install
```
### conda-forge
With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:

View File

@@ -8,6 +8,7 @@
#include "commands/progress.h"
#include "commands/vacuum.h"
#include "hnsw.h"
#include "miscadmin.h"
#include "utils/guc.h"
#include "utils/selfuncs.h"
@@ -28,7 +29,7 @@ static relopt_kind hnsw_relopt_kind;
* this grows bigger, we should use a shmem_request_hook and
* RequestAddinShmemSpace() to pre-reserve space for this.
*/
static void
void
HnswInitLockTranche(void)
{
int *tranche_ids;
@@ -53,6 +54,7 @@ HnswInitLockTranche(void)
void
HnswInit(void)
{
if (!process_shared_preload_libraries_in_progress)
HnswInitLockTranche();
hnsw_relopt_kind = add_reloption_kind();

View File

@@ -389,6 +389,7 @@ void HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation i
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
void HnswLoadNeighbors(HnswElement element, Relation index, int m);
void HnswInitLockTranche(void);
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
/* Index access methods */

View File

@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
Size etupSize;
Size ntupSize;
Size combinedSize;
void *valuePtr = HnswPtrAccess(base, element->value);
Pointer valuePtr = HnswPtrAccess(base, element->value);
/* Update iterator */
iter = element->next;
@@ -601,6 +601,9 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
static void
InitGraph(HnswGraph * graph, char *base, long memoryTotal)
{
/* Initialize the lock tranche if needed */
HnswInitLockTranche();
HnswPtrStore(base, graph->head, (HnswElement) NULL);
HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
graph->memoryUsed = 0;
@@ -974,6 +977,14 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
/* Report less than allocated so never fails */
InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
/*
* Avoid base address for relptr for Postgres < 14.5
* https://github.com/postgres/postgres/commit/7201cd18627afc64850537806da7f22150d1a83b
*/
#if PG_VERSION_NUM < 140005
hnswshared->graphData.memoryUsed += MAXALIGN(1);
#endif
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);

View File

@@ -904,6 +904,27 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
WaitForParallelWorkersToAttach(pcxt);
}
/*
* Compute parallel workers
*/
static int
ComputeParallelWorkers(Relation heap, Relation index)
{
int parallel_workers;
/* Make sure it's safe to use parallel workers */
parallel_workers = plan_create_index_workers(RelationGetRelid(heap), RelationGetRelid(index));
if (parallel_workers == 0)
return 0;
/* Use parallel_workers storage parameter on table if set */
parallel_workers = RelationGetParallelWorkers(heap, -1);
if (parallel_workers != -1)
return Min(parallel_workers, max_parallel_maintenance_workers);
return max_parallel_maintenance_workers;
}
/*
* Scan table for tuples to index
*/
@@ -923,7 +944,7 @@ AssignTuples(IvfflatBuildState * buildstate)
/* Calculate parallel workers */
if (buildstate->heap != NULL)
parallel_workers = plan_create_index_workers(RelationGetRelid(buildstate->heap), RelationGetRelid(buildstate->index));
parallel_workers = ComputeParallelWorkers(buildstate->heap, buildstate->index);
/* Attempt to launch parallel worker scan when required */
if (parallel_workers > 0)

View File

@@ -866,9 +866,10 @@ vector_mul(PG_FUNCTION_ARGS)
int
vector_cmp_internal(Vector * a, Vector * b)
{
CheckDims(a, b);
int dim = Min(a->dim, b->dim);
for (int i = 0; i < a->dim; i++)
/* Check values before dimensions to be consistent with Postgres arrays */
for (int i = 0; i < dim; i++)
{
if (a->x[i] < b->x[i])
return -1;
@@ -876,6 +877,13 @@ vector_cmp_internal(Vector * a, Vector * b)
if (a->x[i] > b->x[i])
return 1;
}
if (a->dim < b->dim)
return -1;
if (a->dim > b->dim)
return 1;
return 0;
}
@@ -889,6 +897,9 @@ vector_lt(PG_FUNCTION_ARGS)
Vector *a = PG_GETARG_VECTOR_P(0);
Vector *b = PG_GETARG_VECTOR_P(1);
/* TODO Remove in 0.7.0 */
CheckDims(a, b);
PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
}
@@ -902,6 +913,9 @@ vector_le(PG_FUNCTION_ARGS)
Vector *a = PG_GETARG_VECTOR_P(0);
Vector *b = PG_GETARG_VECTOR_P(1);
/* TODO Remove in 0.7.0 */
CheckDims(a, b);
PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
}
@@ -915,6 +929,9 @@ vector_eq(PG_FUNCTION_ARGS)
Vector *a = PG_GETARG_VECTOR_P(0);
Vector *b = PG_GETARG_VECTOR_P(1);
/* TODO Remove in 0.7.0 */
CheckDims(a, b);
PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
}
@@ -928,6 +945,9 @@ vector_ne(PG_FUNCTION_ARGS)
Vector *a = PG_GETARG_VECTOR_P(0);
Vector *b = PG_GETARG_VECTOR_P(1);
/* TODO Remove in 0.7.0 */
CheckDims(a, b);
PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
}
@@ -941,6 +961,9 @@ vector_ge(PG_FUNCTION_ARGS)
Vector *a = PG_GETARG_VECTOR_P(0);
Vector *b = PG_GETARG_VECTOR_P(1);
/* TODO Remove in 0.7.0 */
CheckDims(a, b);
PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
}
@@ -954,6 +977,9 @@ vector_gt(PG_FUNCTION_ARGS)
Vector *a = PG_GETARG_VECTOR_P(0);
Vector *b = PG_GETARG_VECTOR_P(1);
/* TODO Remove in 0.7.0 */
CheckDims(a, b);
PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
}

View File

@@ -24,6 +24,56 @@ SELECT '[1e37]'::vector * '[1e37]';
ERROR: value out of range: overflow
SELECT '[1e-37]'::vector * '[1e-37]';
ERROR: value out of range: underflow
SELECT '[1,2,3]'::vector = '[1,2,3]';
?column?
----------
t
(1 row)
SELECT '[1,2,3]'::vector = '[1,2]';
ERROR: different vector dimensions 3 and 2
SELECT vector_cmp('[1,2,3]', '[1,2,3]');
vector_cmp
------------
0
(1 row)
SELECT vector_cmp('[1,2,3]', '[0,0,0]');
vector_cmp
------------
1
(1 row)
SELECT vector_cmp('[0,0,0]', '[1,2,3]');
vector_cmp
------------
-1
(1 row)
SELECT vector_cmp('[1,2]', '[1,2,3]');
vector_cmp
------------
-1
(1 row)
SELECT vector_cmp('[1,2,3]', '[1,2]');
vector_cmp
------------
1
(1 row)
SELECT vector_cmp('[1,2]', '[2,3,4]');
vector_cmp
------------
-1
(1 row)
SELECT vector_cmp('[2,3]', '[1,2,3]');
vector_cmp
------------
1
(1 row)
SELECT vector_dims('[1,2,3]');
vector_dims
-------------

View File

@@ -6,6 +6,17 @@ SELECT '[1,2,3]'::vector * '[4,5,6]';
SELECT '[1e37]'::vector * '[1e37]';
SELECT '[1e-37]'::vector * '[1e-37]';
SELECT '[1,2,3]'::vector = '[1,2,3]';
SELECT '[1,2,3]'::vector = '[1,2]';
SELECT vector_cmp('[1,2,3]', '[1,2,3]');
SELECT vector_cmp('[1,2,3]', '[0,0,0]');
SELECT vector_cmp('[0,0,0]', '[1,2,3]');
SELECT vector_cmp('[1,2]', '[1,2,3]');
SELECT vector_cmp('[1,2,3]', '[1,2]');
SELECT vector_cmp('[1,2]', '[2,3,4]');
SELECT vector_cmp('[2,3]', '[1,2,3]');
SELECT vector_dims('[1,2,3]');
SELECT round(vector_norm('[1,1]')::numeric, 5);